© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1588
    Prev
    Next
    INDEX
    Explanations

    end of enumerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    从而
    1.07
    并且
    1.06
     because
    1.03
    並且
    1.01
     thereby
    1.00
     BECAUSE
    0.95
    然后
    0.92
     并
    0.92
     ហើយ
    0.91
    because
    0.91
    POSITIVE LOGITS
    }}.
    0.92
    ۔
    0.90
    ।
    0.89
    。
    0.87
    }.
    0.80
    ئیں۔
    0.78
    ။
    0.78
    \}.
    0.77
    וף
    0.76
    ᱾
    0.76
    Activations Density 0.173%

    No Known Activations